EPANet: Efficient Path Aggregation Network for Underwater Fish Detection

TL;DR

EPANet is a lightweight, efficient neural network designed for underwater fish detection, integrating multi-scale features and diverse convolutions to improve accuracy and speed over existing methods.

Contribution

The paper introduces EPANet, a novel path aggregation network with a unique feature pyramid and bottleneck structure for enhanced underwater fish detection.

Findings

EPANet achieves higher detection accuracy than state-of-the-art methods.

EPANet maintains low model complexity and fast inference speed.

EPANet outperforms existing approaches on benchmark datasets.

Abstract

Underwater fish detection (UFD) remains a challenging task in computer vision due to low object resolution, significant background interference, and high visual similarity between targets and surroundings. Existing approaches primarily focus on local feature enhancement or incorporate complex attention mechanisms to highlight small objects, often at the cost of increased model complexity and reduced efficiency. To address these limitations, we propose an efficient path aggregation network (EPANet), which leverages complementary feature integration to achieve accurate and lightweight UFD. EPANet consists of two key components: an efficient path aggregation feature pyramid network (EPA-FPN) and a multi-scale diverse-division short path bottleneck (MS-DDSP bottleneck). The EPA-FPN introduces long-range skip connections across disparate scales to improve semantic-spatial complementarity, while cross-layer fusion paths are adopted to enhance feature integration efficiency. The MS-DDSP bottleneck extends the conventional bottleneck structure by introducing finer-grained feature division and diverse convolutional operations, thereby increasing local feature diversity and representation capacity. Extensive experiments on benchmark UFD datasets demonstrate that EPANet outperforms state-of-the-art methods in terms of detection accuracy and inference speed, while maintaining comparable or even lower parameter complexity.